TickerTain
TickerTain
NewsroomShortsPortfolioConvergence
NewsroomShortsPortfolioConvergence
$ANTHROPIC·$MA····$INTC····$BLUE-ORIGIN·$SPCX····$CRWV····$CRM····$MSFT····$NVDA····$ORCL····$CURSOR·$AAPL····$OPENAI·$AMZN····$UBER····$GOOGL····$META····$TSLA····$DATABRICKS·$PERPLEXITY·$LYFT····$NBIS····$TSM····$LITE····$ANDURIL·
$ANTHROPIC·$MA····$INTC····$BLUE-ORIGIN·$SPCX····$CRWV····$CRM····$MSFT····$NVDA····$ORCL····$CURSOR·$AAPL····$OPENAI·$AMZN····$UBER····$GOOGL····$META····$TSLA····$DATABRICKS·$PERPLEXITY·$LYFT····$NBIS····$TSM····$LITE····$ANDURIL·
←

charlie holtz

T2 · manager / operator

Charlie Holtz is the co-founder of Conductor, an AI coding agent orchestration app that lets developers manage multiple concurrent coding agents. The company was part of Y Combinator Summer 2024 batch.

3 calls·3 names·100% bull·last heard 4 months ago·Y Combinator
track record

no scored calls yet — needs a stated position or a categorical verdict, with a matured window vs SPY

top calls

highest conviction · one per company
1sthigh conviction
$CONDUCTORConductorposition

Conductor founder demonstrates AI agent orchestration workflow for coding

Charlie Holtz uses Conductor daily to orchestrate multiple coding agents, treating AI as a workforce where he acts as CEO reviewing PRs; the product enforces opinionated workflows (worktrees, PRs, reviews) to manage agent output at scale.

Y Combinator2026-06episode →
2ndmedium conviction
$ANTHROPICAnthropic

Heavy AI coder prefers Claude Opus for creative feature work over Codex

Charlie Holtz reaches for Claude Opus when building new features because it feels more creative and like a partner, while using fast mode and dangerously accept all permissions for maximum token throughput.

Y Combinator2026-06episode →
3rdmedium conviction
$OPENAIOpenAI

Codex serves as reliable workhorse for debugging and heavy tool-use tasks

Charlie Holtz uses OpenAI's Codex for grinding through specific problems and long debugging sessions because it's not afraid to make many tool calls, complementing Opus for execution-heavy work.

Y Combinator2026-06episode →

most discussed · click a bar to filter

  • $ANTHROPIC
  • $OPENAI
  • $CONDUCTOR

recurring themes

  • AI Coding Agents1
  • AI Infrastructure1
3 total
$ANTHROPIC
Anthropic
MEDcharlie holtz·Y Combinator·4 months ago·Conductor CEO Charlie Holtz Walks Us Through His AI Coding Setup
Heavy AI coder prefers Claude Opus for creative feature work over Codex
Charlie Holtz reaches for Claude Opus when building new features because it feels more creative and like a partner, while using fast mode and dangerously accept all permissions for maximum token throughput.
"Cloud I'll reach for when I want a little more like back and forth. I feel like Opus is just like a little more creative, like a little more of a partner. And so I would say like…"
10:45
$OPENAI
OpenAI
MEDcharlie holtz·Y Combinator·4 months ago·Conductor CEO Charlie Holtz Walks Us Through His AI Coding Setup
Codex serves as reliable workhorse for debugging and heavy tool-use tasks
Charlie Holtz uses OpenAI's Codex for grinding through specific problems and long debugging sessions because it's not afraid to make many tool calls, complementing Opus for execution-heavy work.
"Codex is like the workhorse. It will power through like a specific problem or like uh it's not afraid to do a ton of tool calls and like debug something with me for a long time."
10:45
$CONDUCTOR
Conductor
HIGHcharlie holtz·Y Combinator·4 months ago·Conductor CEO Charlie Holtz Walks Us Through His AI Coding Setup· position
Conductor founder demonstrates AI agent orchestration workflow for coding
Charlie Holtz uses Conductor daily to orchestrate multiple coding agents, treating AI as a workforce where he acts as CEO reviewing PRs; the product enforces opinionated workflows (worktrees, PRs, reviews) to manage agent output at scale.
"I spend most of my day in Conductor. We're using Conductor to build Conductor. One thing that I do is I'm constantly kicking off new tasks... A big part of how I use Conductor is…"
0:44
8
AI Coding Agentstailwind
AI coding shifts from writing code to orchestrating agent fleets with prompts as core IP
Charlie Holtz describes a workflow where he manages multiple concurrent AI agents like a conductor, reviewing PRs rather than writing code; he argues code becomes 'sawdust' while prompts become the durable asset that can be re-run on future models.
7
AI Infrastructuretailwind
Local model inference and massive token spend signal compute shift to inference-time scaling
Holtz runs local TTS (Parakeet) on 128GB RAM Mac, spends $22k/month on API tokens, and anticipates agents running 10x longer in cloud environments unconstrained by local hardware, highlighting inference compute demand.